ENH: str.replace accepts a compiled expression

- .str.replace now accepts a compiled regular expression for `pat`.
- Signature for .str.replace changed, but remains backwards compatible.

See #15446

Author: rouzazari

doc/source/whatsnew/v0.20.0.txt

@@ -28,6 +28,7 @@ New features
 
 - Integration with the ``feather-format``, including a new top-level ``pd.read_feather()`` and ``DataFrame.to_feather()`` method, see :ref:`here <io.feather>`.
 - ``.str.replace`` now accepts a callable, as replacement, which is passed to ``re.sub`` (:issue:`15055`)
+- ``.str.replace`` now accepts a compiled regular expression as pattern (:issue:`15446`)
 
 
 

pandas/core/strings.py

@@ -9,7 +9,8 @@
                                  is_string_like,
                                  is_list_like,
                                  is_scalar,
-                                 is_integer)
+                                 is_integer,
+                                 is_re)
 from pandas.core.common import _values_from_object
 
 from pandas.core.algorithms import take_1d
@@ -303,16 +304,20 @@ def str_endswith(arr, pat, na=np.nan):
     return _na_map(f, arr, na, dtype=bool)
 
 
-def str_replace(arr, pat, repl, n=-1, case=True, flags=0):
+def str_replace(arr, pat, repl, n=-1, case=None, flags=None):
     """
     Replace occurrences of pattern/regex in the Series/Index with
     some other string. Equivalent to :meth:`str.replace` or
     :func:`re.sub`.
 
     Parameters
     ----------
-    pat : string
-        Character sequence or regular expression
+    pat : string or compiled regex
+        String can be a character sequence or regular expression.
+
+        .. versionadded:: 0.20.0
+            `pat` also accepts a compiled regex.
+
     repl : string or callable
         Replacement string or a callable. The callable is passed the regex
         match object and must return a replacement string to be used.
@@ -323,10 +328,11 @@ def str_replace(arr, pat, repl, n=-1, case=True, flags=0):
 
     n : int, default -1 (all)
         Number of replacements to make from start
-    case : boolean, default True
-        If True, case sensitive
-    flags : int, default 0 (no flags)
-        re module flags, e.g. re.IGNORECASE
+    case : boolean, default None (case sensitive)
+        If False, case insensitive. Must be None if `pat` is a compiled regex.
+    flags : int, default None (no flags)
+        re module flags, e.g. re.IGNORECASE. Must be None if `pat` is a
+        compiled regex.
 
     Returns
     -------
@@ -372,21 +378,48 @@ def str_replace(arr, pat, repl, n=-1, case=True, flags=0):
     0    tWO
     1    bAR
     dtype: object
+
+    When `pat` is a compiled regex, all flags should be included in the
+    compiled regex. Use of `case` or `flags` with a compiled regex will
+    raise an error.
+
+    >>> regex_pat = re.compile(r'FUZ', flags=re.IGNORECASE)
+    >>> pd.Series(['foo', 'fuz', np.nan]).str.replace(regex_pat, 'bar')
+    0    foo
+    1    bar
+    2    NaN
+    dtype: object
     """
 
     # Check whether repl is valid (GH 13438, GH 15055)
     if not (is_string_like(repl) or callable(repl)):
         raise TypeError("repl must be a string or callable")
-    use_re = not case or len(pat) > 1 or flags or callable(repl)
 
-    if use_re:
-        if not case:
+    is_compiled_re = is_re(pat)
+    if is_compiled_re:
+        if (case is not None) or (flags is not None):
+            raise ValueError("case and flags must be None"
+                             " when pat is a compiled regex")
+        # Python2's re.sub requires that flag is an int
+        if compat.PY2:
+            flags = 0
+    else:
+        # not a compiled regex
+        # set default case/flags
+        if case is None:
+            case = True
+        if flags is None:
+            flags = 0
+        # add case flag, if provided
+        if case is False:
             flags |= re.IGNORECASE
-        regex = re.compile(pat, flags=flags)
-        n = n if n >= 0 else 0
 
-        def f(x):
-            return regex.sub(repl, x, count=n)
+    use_re = is_compiled_re or len(pat) > 1 or flags or callable(repl)
+
+    if use_re:
+        n = n if n >= 0 else 0
+        f = lambda x: re.sub(pattern=pat, repl=repl, string=x,
+                             count=n, flags=flags)
     else:
         f = lambda x: x.replace(pat, repl, n)
 
@@ -1558,7 +1591,7 @@ def match(self, pat, case=True, flags=0, na=np.nan, as_indexer=False):
         return self._wrap_result(result)
 
     @copy(str_replace)
-    def replace(self, pat, repl, n=-1, case=True, flags=0):
+    def replace(self, pat, repl, n=-1, case=None, flags=None):
         result = str_replace(self._data, pat, repl, n=n, case=case,
                              flags=flags)
         return self._wrap_result(result)

pandas/tests/test_strings.py

@@ -469,6 +469,62 @@ def test_replace_callable(self):
         exp = Series(['bAR', NA])
         tm.assert_series_equal(result, exp)
 
+    def test_replace_compiled_regex(self):
+        # GH 15446
+        values = Series(['fooBAD__barBAD', NA])
+
+        # test with compiled regex
+        pat = re.compile(r'BAD[_]*')
+        result = values.str.replace(pat, '')
+        exp = Series(['foobar', NA])
+        tm.assert_series_equal(result, exp)
+
+        # mixed
+        mixed = Series(['aBAD', NA, 'bBAD', True, datetime.today(), 'fooBAD',
+                        None, 1, 2.])
+
+        rs = Series(mixed).str.replace(pat, '')
+        xp = Series(['a', NA, 'b', NA, NA, 'foo', NA, NA, NA])
+        tm.assertIsInstance(rs, Series)
+        tm.assert_almost_equal(rs, xp)
+
+        # unicode
+        values = Series([u('fooBAD__barBAD'), NA])
+
+        result = values.str.replace(pat, '')
+        exp = Series([u('foobar'), NA])
+        tm.assert_series_equal(result, exp)
+
+        result = values.str.replace(pat, '', n=1)
+        exp = Series([u('foobarBAD'), NA])
+        tm.assert_series_equal(result, exp)
+
+        # flags + unicode
+        values = Series([b"abcd,\xc3\xa0".decode("utf-8")])
+        exp = Series([b"abcd, \xc3\xa0".decode("utf-8")])
+        pat = re.compile(r"(?<=\w),(?=\w)", flags=re.UNICODE)
+        result = values.str.replace(pat, ", ")
+        tm.assert_series_equal(result, exp)
+
+        # case and flags provided to str.replace will have no effect
+        # and will produce warnings
+        values = Series(['fooBAD__barBAD__bad', NA])
+        pat = re.compile(r'BAD[_]*')
+
+        with tm.assertRaisesRegexp(ValueError, "case and flags must be None"):
+            result = values.str.replace(pat, '', flags=re.IGNORECASE)
+
+        with tm.assertRaisesRegexp(ValueError, "case and flags must be None"):
+            result = values.str.replace(pat, '', case=False)
+
+        # test with callable
+        values = Series(['fooBAD__barBAD', NA])
+        repl = lambda m: m.group(0).swapcase()
+        pat = re.compile('[a-z][A-Z]{2}')
+        result = values.str.replace(pat, repl, n=2)
+        exp = Series(['foObaD__baRbaD', NA])
+        tm.assert_series_equal(result, exp)
+
     def test_repeat(self):
         values = Series(['a', 'b', NA, 'c', NA, 'd'])